Training in progress, step 31600, checkpoint

last-checkpoint/README.md

@@ -1187,6 +1187,8 @@ You can finetune this model on your own dataset.
 </details>
 
 ### Training Logs
+<details><summary>Click to expand</summary>
+
 | Epoch  | Step  | Training Loss |
 |:------:|:-----:|:-------------:|
 | 0.4674 | 26450 | 0.3511        |
@@ -1289,7 +1291,12 @@ You can finetune this model on your own dataset.
 | 0.5531 | 31300 | 0.4005        |
 | 0.5540 | 31350 | 0.2993        |
 | 0.5549 | 31400 | 0.3463        |
+| 0.5557 | 31450 | 0.3654        |
+| 0.5566 | 31500 | 0.3329        |
+| 0.5575 | 31550 | 0.2794        |
+| 0.5584 | 31600 | 0.4189        |
 
+</details>
 
 ### Framework Versions
 - Python: 3.11.13

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61791a9f27b2e84e2748c75d563b418265e6d5395cbf211b0cd0f03e7a800569
+oid sha256:037af2d441f69bccfeb282dafbe011432348a180c3a824cdedd50370b13aa3f5
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18bdca8989ebbde834c52a39d768225227cd3368f6e914278dbdb9e94069701f
+oid sha256:cd0170e06425554bee01ebe42a564ab7255970144350ac51e311ccbc99405281
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90c0f464ce2d63e5775d5f69a53393003698611f7c0fd1450ee54986328e19d1
+oid sha256:8a18c03e60472d4b8f510c853a2c7471950a1574efd6c20fb49cc26f42e6d1dd
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d8621fe1648dc96d7d6a12a9e96d1ea20e9a16f5271880935750dfe7f0b53b1
+oid sha256:c19235faf86fc7b488d049c5de2dd9270a2ad7d80400a9f4692705e68f0f698f
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8192cf6ea07163c3522a31666ef2d6f88f70490e78651f44e286f3d02a1bce81
+oid sha256:a676db8a1d42fae190e3de7197b8ccb119e27d8c3e860a70915ea0b98f39452b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5548585464119736,
+  "epoch": 0.5583926772808397,
   "eval_steps": 500,
-  "global_step": 31400,
+  "global_step": 31600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4404,6 +4404,34 @@
       "learning_rate": 2.4741316683355912e-05,
       "loss": 0.3463,
       "step": 31400
+    },
+    {
+      "epoch": 0.5557420791291902,
+      "grad_norm": 1.5994555950164795,
+      "learning_rate": 2.4692230665017377e-05,
+      "loss": 0.3654,
+      "step": 31450
+    },
+    {
+      "epoch": 0.5566256118464067,
+      "grad_norm": 1.528947114944458,
+      "learning_rate": 2.4643144646678842e-05,
+      "loss": 0.3329,
+      "step": 31500
+    },
+    {
+      "epoch": 0.5575091445636232,
+      "grad_norm": 1.4391777515411377,
+      "learning_rate": 2.4594058628340306e-05,
+      "loss": 0.2794,
+      "step": 31550
+    },
+    {
+      "epoch": 0.5583926772808397,
+      "grad_norm": 4.419312953948975,
+      "learning_rate": 2.4544972610001768e-05,
+      "loss": 0.4189,
+      "step": 31600
     }
   ],
   "logging_steps": 50,